论文部分内容阅读
介绍了耦合神经网络的工艺设计实例推理系统的实现方法论，提出了一种基于神经网络的工艺设计实例推理索引模型．与现存大多数实例推理系统不同，该方法用神经网络实现实例的动态分类和索引．实例层次分类的三层结构和基于特征的聚类模板概念，为实现基于符号处理的实例推理求解模式向基于神经计算的模式识别求解模式映射提供了条件．提出了基于实例的工艺知识获取模型，采用新实例的入库操作实现工艺知识的隐式获取，从而使知识获取得以简化．神经网络的自适应、自学习能力将减少系统的日常维护工作．基于实例的系统可望解决知识获取的难题．
This paper introduces the realization methodology of process designing case inference system based on coupled neural network, and proposes an example inference indexing model of process design based on neural network. Unlike most existing case inference systems, this method uses neural networks to dynamically classify and index instances. The three-level structure of instance-level classification and the concept of cluster-based template based on feature provide the conditions for implementing instance-based reasoning solution based on symbolic processing and pattern recognition based on neural computing. An instance-based process knowledge acquisition model was proposed. Implicit acquisition of process knowledge was implemented by using a new instance of in-warehouse operation, so that knowledge acquisition could be simplified. Neural network adaptation, self-learning ability will reduce the system’s routine maintenance work. Instance-based systems are expected to solve the problem of knowledge acquisition.